Combinations of removable workload optimized modules for implementing different application workloads

Abstract

According to an example, configurable workload optimization may include selecting a performance optimized application workload from available performance optimized application workloads. A predetermined combination of removable workload optimized modules may be selected to implement the selected performance optimized application workload. Different combinations of the removable workload optimized modules may be usable to implement different ones of the available performance optimized application workloads. The predetermined combination of the removable workload optimized modules may be managed to implement the selected performance optimized application workload. Data flows directed to the predetermined combination of the removable workload optimized modules may be received. The data flows may be analyzed based on attributes of the data flows, and redirected for processing by one of the removable workload optimized modules of the predetermined combination of the removable workload optimized modules based on the analysis.

What is claimed is: 
     
       1. A non-transitory computer readable medium having stored thereon machine readable instructions to provide configurable workload optimization, the machine readable instructions, when executed, cause at least one processor to:
 select a performance optimized application workload from a plurality of available performance optimized application workloads; 
 select a predetermined combination of a plurality of removable workload optimized modules to implement the selected performance optimized application workload, wherein different combinations of the plurality of removable workload optimized modules are usable to implement different ones of the plurality of available performance optimized application workloads; 
 manage the predetermined combination of the plurality of removable workload optimized modules to implement the selected performance optimized application workload; 
 receive data flows directed to the predetermined combination of the plurality of removable workload optimized modules; 
 analyze the data flows based on attributes of the data flows; and 
 redirect the data flows for processing by at least one of the plurality of removable workload optimized modules of the predetermined combination of the plurality of removable workload optimized modules based on the analysis, 
 wherein the selected performance optimized application workload includes intrusion prevention, and the predetermined combination of the plurality of removable workload optimized modules includes a network processing unit (NPU) module, and a field-programmable gate array (FPGA) module to implement intrusion prevention functionality. 
 
     
     
       2. The non-transitory computer readable medium of  claim 1 , wherein to redirect the data flows for processing by at least one of the plurality of removable workload optimized modules of the predetermined combination of the plurality of removable workload optimized modules based on the analysis, the machine readable instructions, when executed, further cause the at least one processor to:
 redirect a subset of the data flows based on the analysis for processing by the predetermined combination of the plurality of removable workload optimized modules; and 
 prevent a remaining subset of the data flows from being directed to the predetermined combination of the plurality of removable workload optimized modules. 
 
     
     
       3. The non-transitory computer readable medium of  claim 1 , wherein to redirect the data flows for processing by at least one of the plurality of removable workload optimized modules of the predetermined combination of the plurality of removable workload optimized modules based on the analysis, the machine readable instructions, when executed, further cause the at least one processor to:
 separate incoming packets of the data flows into a known approved category that includes packets that show no signs of containing attacks, and forward the approved category packets to their intended destinations; 
 separate incoming packets of the data flows into a known disapproved category that includes packets that are to be dropped, and drop the disapproved category packets; and 
 separate incoming packets of the data flows into a suspicious category that includes packets that need further inspection, and forward the suspicious category packets for further analysis. 
 
     
     
       4. The non-transitory computer readable medium of  claim 1 , further comprising machine readable instructions, that when executed, cause the at least one processor to:
 use a cluster fabric to interconnect a plurality of slots, wherein each slot of the plurality of slots corresponds to each of the plurality of removable workload optimized modules. 
 
     
     
       5. A method for configurable workload optimization, the method comprising:
 selecting a plurality of performance optimized application workloads from a plurality of available performance optimized application workloads; 
 selecting predetermined combinations of a plurality of removable workload optimized modules to implement the selected performance optimized application workloads, wherein different combinations of the plurality of removable workload optimized modules are usable to implement different ones of the plurality of available performance optimized application workloads; 
 managing, by at least one processor, the predetermined combinations of the plurality of removable workload optimized modules to implement the selected performance optimized application workloads; 
 receiving data flows directed to the predetermined combinations of the plurality of removable workload optimized modules; 
 analyzing the data flows based on attributes of the data flows; and 
 redirecting the data flows for processing by at least one of the plurality of removable workload optimized modules of the predetermined combinations of the plurality of removable workload optimized modules based on the analysis, 
 wherein redirecting the data flows for processing by at least one of the plurality of removable workload optimized modules of the predetermined combinations of the plurality of removable workload optimized modules based on the analysis, the method further comprises: 
 separating incoming packets of the data flows into a known approved category that includes packets that show no signs of containing attacks, and forwarding the approved category packets to their intended destinations; 
 separating incoming packets of the data flows into a known disapproved category that includes packets that are to be dropped, and dropping the disapproved category packets; and 
 separating incoming packets of the data flows into a suspicious category that includes packets that need further inspection, and forwarding the suspicious category packets for further analysis. 
 
     
     
       6. The method of  claim 5 , further comprising:
 using a cluster fabric to interconnect a plurality of slots, wherein each slot of the plurality of slots corresponds to each of the plurality of removable workload optimized modules. 
 
     
     
       7. The method of  claim 5 , wherein a selected performance optimized application workload of the plurality of the selected performance optimized application workloads includes intrusion prevention, and a predetermined combination of the plurality of removable workload optimized modules includes a network processing unit (NPU) module, and a field-programmable gate array (FPGA) module to implement intrusion prevention functionality. 
     
     
       8. A non-transitory computer readable medium having stored thereon machine readable instructions to provide configurable workload optimization, the machine readable instructions, when executed, cause at least one processor to:
 select a performance optimized application workload from a plurality of available performance optimized application workloads; 
 select a predetermined combination of a plurality of removable workload optimized modules to implement the selected performance optimized application workload, wherein different combinations of the plurality of removable workload optimized modules are usable to implement different ones of the plurality of available performance optimized application workloads; 
 manage the predetermined combination of the plurality of removable workload optimized modules to implement the selected performance optimized application workload; 
 receive data flows directed to the predetermined combination of the plurality of removable workload optimized modules; 
 analyze the data flows based on attributes of the data flows; and 
 redirect the data flows for processing by at least one of the plurality of removable workload optimized modules of the predetermined combination of the plurality of removable workload optimized modules based on the analysis, 
 wherein the selected performance optimized application workload includes intrusion prevention, the plurality of removable workload optimized modules include a graphics processing unit (GPU) module, a network processing unit (NPU) module, a digital signal processing (DSP) module, and a field-programmable gate array (FPGA) module, and the predetermined combination of the plurality of removable workload optimized modules includes the NPU module, and the FPGA module to implement intrusion prevention functionality. 
 
     
     
       9. The non-transitory computer readable medium of  claim 8 , wherein to redirect the data flows for processing by at least one of the plurality of removable workload optimized modules of the predetermined combination of the plurality of removable workload optimized modules based on the analysis, the machine readable instructions, when executed, further cause the at least one processor to:
 redirect a subset of the data flows based on the analysis for processing by the predetermined combination of the plurality of removable workload optimized modules; and 
 prevent a remaining subset of the data flows from being directed to the predetermined combination of the plurality of removable workload optimized modules. 
 
     
     
       10. The non-transitory computer readable medium of  claim 8 , further comprising machine readable instructions, that when executed, cause the at least one processor to:
 use a cluster fabric to interconnect a plurality of slots, wherein each slot of the plurality of slots corresponds to each of the plurality of removable workload optimized modules. 
 
     
     
       11. A non-transitory computer readable medium having stored thereon machine readable instructions to provide configurable workload optimization, the machine readable instructions, when executed, cause at least one processor to:
 select a performance optimized application workload from a plurality of available performance optimized application workloads; 
 select a predetermined combination of a plurality of removable workload optimized modules to implement the selected performance optimized application workload, wherein different combinations of the plurality of removable workload optimized modules are usable to implement different ones of the plurality of available performance optimized application workloads; 
 manage the predetermined combination of the plurality of removable workload optimized modules to implement the selected performance optimized application workload; 
 receive data flows directed to the predetermined combination of the plurality of removable workload optimized modules; 
 analyze the data flows based on attributes of the data flows; and 
 redirect the data flows for processing by at least one of the plurality of removable workload optimized modules of the predetermined combination of the plurality of removable workload optimized modules based on the analysis, 
 wherein to redirect the data flows for processing by at least one of the plurality of removable workload optimized modules of the predetermined combination of the plurality of removable workload optimized modules based on the analysis, the machine readable instructions, when executed, further cause the at least one processor to: 
 separate incoming packets of the data flows into a known approved category that includes packets that show no signs of containing attacks, and forward the approved category packets to their intended destinations; 
 separate incoming packets of the data flows into a known disapproved category that includes packets that are to be dropped, and drop the disapproved category packets; and 
 separate incoming packets of the data flows into a suspicious category that includes packets that need further inspection, and forward the suspicious category packets for further analysis. 
 
     
     
       12. The non-transitory computer readable medium of  claim 11 , further comprising machine readable instructions, that when executed, cause the at least one processor to:
 use a cluster fabric to interconnect a plurality of slots, wherein each slot of the plurality of slots corresponds to each of the plurality of removable workload optimized modules. 
 
     
     
       13. A method for configurable workload optimization, the method comprising:
 selecting a plurality of performance optimized application workloads from a plurality of available performance optimized application workloads; 
 selecting predetermined combinations of a plurality of removable workload optimized modules to implement the selected performance optimized application workloads, wherein different combinations of the plurality of removable workload optimized modules are usable to implement different ones of the plurality of available performance optimized application workloads; 
 managing, by at least one processor, the predetermined combinations of the plurality of removable workload optimized modules to implement the selected performance optimized application workloads; 
 receiving data flows directed to the predetermined combinations of the plurality of removable workload optimized modules; 
 analyzing the data flows based on attributes of the data flows; and 
 redirecting the data flows for processing by at least one of the plurality of removable workload optimized modules of the predetermined combinations of the plurality of removable workload optimized modules based on the analysis, 
 wherein a selected performance optimized application workload of the plurality of the selected performance optimized application workloads includes intrusion prevention, and a predetermined combination of the plurality of removable workload optimized modules includes a network processing unit (NPU) module, and a field-programmable gate array (FPGA) module to implement intrusion prevention functionality. 
 
     
     
       14. The method of  claim 13 , further comprising:
 using a cluster fabric to interconnect a plurality of slots, wherein each slot of the plurality of slots corresponds to each of the plurality of removable workload optimized modules.